1

Two-Scale Latent Dynamics for Recurrent-Depth Transformers
Recurrent-depth transformers scale test-time compute by iterating latent computations before emitting tokens. We study the geometry of …
Cite arXiv
Two-Scale Latent Dynamics for Recurrent-Depth Transformers
Membership and Dataset Inference Attacks on Large Audio Generative Models
Generative audio models, based on diffusion and autoregressive architectures, have advanced rapidly in both quality and expressiveness. …
Cite
Membership and Dataset Inference Attacks on Large Audio Generative Models
Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing
Neural fields have emerged as a powerful representation for 3D geometry, enabling compact and continuous modeling of complex shapes. …
Cite arXiv GitHub
Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing
On Task Vectors and Gradients
Task arithmetic has emerged as a simple yet powerful technique for model merging, enabling the combination of multiple finetuned models …
Cite arXiv
On Task Vectors and Gradients
Foundation Models on a Budget: Approximating Blocks in Large Vision Models
Deep neural networks often learn similar internal representations, both across different models and within their own layers. While …
Cite arXiv
Foundation Models on a Budget: Approximating Blocks in Large Vision Models
LoopGen: Training-Free Loopable Music Generation
Loops–short audio segments designed for seamless repetition–are central to many music genres, particularly those rooted in …
Cite arXiv
LoopGen: Training-Free Loopable Music Generation
STAGE: Stemmed Accompaniment Generation through Prefix-Based Conditioning
Recent advances in generative models have made it possible to create high-quality, coherent music, with some systems delivering …
Cite arXiv GitHub
STAGE: Stemmed Accompaniment Generation through Prefix-Based Conditioning
Mergenetic: a Simple Evolutionary Model Merging Library
Model merging allows combining the capabilities of existing models into a new one - post hoc, without additional training. This has …
Cite arXiv GitHub
Mergenetic: a Simple Evolutionary Model Merging Library
MERGE3: Efficient Evolutionary Merging on Consumer-grade GPUs
Evolutionary model merging enables the creation of high-performing multi-task models but remains computationally prohibitive for …
Cite arXiv GitHub
MERGE3: Efficient Evolutionary Merging on Consumer-grade GPUs
Update Your Transformer to the Latest Release: Re-Basin of Task Vectors
Foundation models serve as the backbone for numerous specialized models developed through fine-tuning. However, when the underlying …
Cite URL
Update Your Transformer to the Latest Release: Re-Basin of Task Vectors